most citedLGViT: Dynamic Early Exiting for Accelerating Vision Transformer

31 citations · 39 across the 7 of their papers we have counts for

collaborators

7 papers

cs.SE20232 cited

Pairwise GUI Dataset Construction Between Android Phones and Tablets

Han Hu, Haolan Zhan, Yujin Huang +1

In the current landscape of pervasive smartphones and tablets, apps frequently exist across both platforms. Although apps share most graphic user interfaces (GUIs) and functionalit…

cs.CV20231 cited

DeViT: Decomposing Vision Transformers for Collaborative Inference in Edge Devices

Guanyu Xu, Zhiwei Hao, Yong Luo +3

Recent years have witnessed the great success of vision transformer (ViT), which has achieved state-of-the-art performance on multiple computer vision benchmarks. However, ViT mode…

cs.CV20234 cited

Mask-Attention-Free Transformer for 3D Instance Segmentation

Xin Lai, Yuhui Yuan, Ruihang Chu +3

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial insta…

cs.LG20231 cited

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

Shiyuan Zuo, Rongfei Fan, Han Hu +2

In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks. At each user, model parameter is firstly…

cs.LG2023

Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning

Xuming An, Rongfei Fan, Shiyuan Zuo +3

Federated learning (FL) has emerged as an appealing machine learning approach to deal with massive raw data generated at multiple mobile devices, {which needs to aggregate the trai…

cs.CV202331 cited

LGViT: Dynamic Early Exiting for Accelerating Vision Transformer

Guanyu Xu, Jiawei Hao, Li Shen +4

Recently, the efficient deployment and acceleration of powerful vision transformers (ViTs) on resource-limited edge devices for providing multimedia services have become attractive…